Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2577 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1831. Min Range: -2.1831

Max Act: 2.0979. Min Act: -0.0000

Data Index: 1330384 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.1831. Min Range: -2.1831

Max Act: 2.1831. Min Act: -0.0000

Data Index: 962602 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 2.1831. Min Range: -2.1831

Max Act: 2.1221. Min Act: -0.0000

Data Index: 952834 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 2.1831. Min Range: -2.1831

Max Act: 2.1467. Min Act: -0.0000

Data Index: 152991 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7419. Min Act: -0.0000

Data Index: 1419689 (Python Code)

Max Activating Token Index: 811

Text #5

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7164. Min Act: -0.0000

Data Index: 590417 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.8129. Min Act: -0.0000

Data Index: 241660 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7014. Min Act: -0.0000

Data Index: 244041 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1223921 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7743. Min Act: -0.0000

Data Index: 522913 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7630. Min Act: -0.0000

Data Index: 173242 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7462. Min Act: -0.0000

Data Index: 651096 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.8170. Min Act: -0.0000

Data Index: 479461 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.7739. Min Act: -0.0000

Data Index: 1064090 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.5637. Min Act: -0.0000

Data Index: 583187 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.6231. Min Act: -0.0000

Data Index: 110448 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.6133. Min Act: -0.0000

Data Index: 531531 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.5824. Min Act: -0.0000

Data Index: 1341031 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.5766. Min Act: -0.0000

Data Index: 278520 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 2.1831. Min Range: -2.1831

Max Act: 1.6670. Min Act: -0.0000

Data Index: 1207039 (C4 (Web Text))

Max Activating Token Index: 907